# Representing 3D Faces with Learnable B-Spline Volumes

Source: [Representing 3D Faces with Learnable B-Spline Volumes](<https://www.sota2.com/research/paper/69df1bc57d0172140ec7bb9f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-16T05:00:11.996Z

Authors: Prashanth Chandran, Daoye Wang, Timo Bolkart

Published: 2026-04-14T15:42:48.000Z

## Abstract

We present CUBE (Control-based Unified B-spline Encoding), a new geometric representation for human faces that combines B-spline volumes with learned features, and demonstrate its use as a decoder for 3D scan registration and monocular 3D face reconstruction. Unlike existing B-spline representations with 3D control points, CUBE is parametrized by a lattice (e.g., 8 x 8 x 8) of high-dimensional control features, increasing the model's expressivity. These features define a continuous, two-stage mapping from a 3D parametric domain to 3D Euclidean space via an intermediate feature space. First, high-dimensional control features are locally blended using the B-spline bases, yielding a high-dimensional feature vector whose first three values define a 3D base mesh. A small MLP then processes this feature vector to predict a residual displacement from the base shape, yielding the final refined 3D coordinates. To reconstruct 3D surfaces in dense semantic correspondence, CUBE is queried at 3D coordinates sampled from a fixed template mesh. Crucially, CUBE retains the local support property of traditional B-spline representations, enabling local surface editing by updating individual control features. We demonstrate the strengths of this representation by training transformer-based encoders to predict CUBE's control features from unstructured point clouds and monocular images, achieving state-of-the-art scan registration results compared to recent baselines.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [3D Facial Scan Registration on 3D Facial Scans](<https://www.sota2.com/research/sota/3d-facial-scan-registration-on-3d-facial-scans.md>): 3D Facial Scan Registration; 3D Facial Scans; Mean PTS Error (mm): 0.95.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.12894>)

[PDF](<https://arxiv.org/pdf/2604.12894.pdf>)
